Dyte MCP for AI. Control all video meetings, recordings, and live streams via your agent.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
Dyte MCP gives your AI agent full control over real-time video and audio infrastructure. Use it to automatically create meetings, manage participants joining a session, start or stop recordings, and broadcast live streams directly through conversation.
What AI agents can do with Dyte Automation
Add participant
Adds a specific user to an active video meeting room.
Create meeting
Schedules and sets up a brand new Dyte virtual meeting.
Create webhook
Establishes a real-time notification endpoint for tracking meeting lifecycle events.
Instantly create new meetings and fetch a list of existing meeting details.
Add specific users to an ongoing meeting and get the authentication tokens needed for client applications.
Start or stop live streaming sessions for a designated meeting room.
Initiate a recording, configure storage options, and retrieve details or download links for completed recordings.
Set up webhooks to receive real-time notifications when meetings start or end.
Ask an AI about this
Waiting for input…
What AI agents can do with Dyte: 11 Tools for Video Communication
These tools give your agent direct access to every function needed to create, manage, broadcast, record, and track real-time video meetings.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Dyte on VinkiusAdd Participant
Adds a specific user to an active video meeting room.
Create Meeting
Schedules and sets up a brand new Dyte virtual meeting.
Create Webhook
Establishes a real-time notification endpoint for tracking meeting lifecycle events.
Get Meeting
Retrieves all current details about a specific scheduled meeting room.
Get Recording
Fetches the status and download link for an existing recording asset.
List Meetings
Retrieves a list of all meetings associated with your organization.
List Participants
Lists every user currently present in an active meeting session.
Start Livestream
Begins broadcasting a live stream of the current meeting to external audiences.
Start Recording
Starts capturing video and audio for an active meeting, allowing custom storage...
Stop Livestream
Ends the public broadcast of a live stream.
Stop Recording
Halts any active recording session in the meeting.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Dyte integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Dyte, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Dyte. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 11 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Coordinating Live Video Calls Used To Be a Pain Point, Solved with Vinkius AI Gateway
Right now, setting up or modifying a video meeting means jumping between multiple platforms and APIs. You might first need to call an endpoint just to create the room ID. Then, if you want to invite someone, you have to hit a different API to add them, and if you're doing a webinar, another set of steps is needed to configure streaming permissions.
With this MCP, your AI agent handles that entire chain of events. You simply ask it what you need done—like starting a recording for an existing meeting—and the system executes all the necessary commands behind the scenes. You just get the result: the recording starts.
Dyte MCP Gives Your Agent Full Video Control
You eliminate the need for brittle, multi-step integration code. No more writing separate logic blocks to handle participant fetching versus starting a stream; those actions are grouped and managed.
Now, managing your entire video infrastructure is as simple as giving a command. It's that clean.
What your AI can actually do with this
This MCP lets you connect your organization's entire video communication workflow directly into your AI agent. Instead of writing boilerplate code for every meeting setup, your system can now act as a backend controller for all real-time interactions. You can automate everything from setting up instant conference rooms to managing the full lifecycle of recorded assets and live broadcasts.
For example, you can tell your agent to set up a new meeting room and immediately add specific users before the call even starts. It handles participant management, allowing you to generate necessary tokens for your frontend SDKs in one step. You can also programmatically start or stop recordings, configuring custom storage like AWS S3, and then manage any associated live streams.
Because Vinkius hosts this MCP, your AI client gains access to the entire suite of video tools without needing multiple API keys or complex integrations.
019ea5e8-8991-70b1-b2cd-7b89c401fb06 
Here's how it actually works
The bottom line is you control complex, real-time communication workflows by talking to your AI agent instead of writing code.
Subscribe to this MCP and enter your required Dyte Organization ID and API Key credentials.
Your AI agent connects, giving it full access to the video infrastructure tools.
You issue a natural language command—like 'Start a meeting for Marketing'—and the MCP executes the necessary steps.
Who is this actually for?
This is for technical teams who deal with high volumes of scheduled or ad-hoc video calls. If you're tired of manually calling multiple APIs just to get a meeting set up, this MCP lets your agent handle the whole sequence.
Integrates live communication features into an application by accessing video management tools directly through their AI client.
Monitors and automates meeting status, adding participants or listing recordings simply by chatting with the agent to track progress.
Automates the creation of webinar rooms for internal training sessions, ensuring proper participant access and recording setups are handled automatically.
What Changes When You Connect
Automate Meeting Setup: Instead of calling multiple APIs to get a room running, you can use create_meeting in one prompt to schedule the entire session instantly.
Manage Attendees Effortlessly: You can add users using add_participant and automatically generate the necessary auth tokens for your frontend application.
Full Recording Lifecycle: Start recordings with start_recording, stop them with stop_recording, and then use get_recording to get a download URL, all through conversation.
Broadcasting Control: Need to go live? Use start_livestream to broadcast the meeting, and when you're done, just send a command to stop_livestream.
Stay Updated with Webhooks: Set up event tracking using create_webhook, so your agent knows exactly when meetings start or end without needing constant polling.
See it in action
Onboarding a New Client
The Ops Engineer needs to set up a group interview. They prompt their agent: 'Create meeting room A, then add participants Alice and Bob.' The agent uses create_meeting and add_participant, handling the setup in two steps.
Live Training Session
The Product Manager needs to run a webinar. They tell their agent: 'Start recording for this meeting, configure it for S3 storage.' The agent uses start_recording and manages the custom configuration details.
Post-Meeting Cleanup
A user asks their agent: 'What happened in that call yesterday?' The agent first uses list_meetings to find the ID, then calls get_recording to fetch the download link for review.
Crisis Communications
The Operations Team needs immediate visibility. They tell their agent: 'List all participants in Meeting X and check if we are currently livestreaming.' The agent runs list_participants and checks the live status using available tools.
The honest tradeoffs
Handling multiple steps manually
Having to log into the Dyte dashboard, click 'Create Meeting,' fill out forms, then go back and find the participant list to add people.
Instead, ask your agent: 'Schedule a meeting for next week and invite Jane.' The MCP handles both create_meeting and potential participant addition in one sequence.
Forgetting required tokens
Successfully adding a participant but then needing to manually fetch the auth token before the frontend can actually connect.
Use add_participant. The MCP handles both the addition and generates the necessary authentication token for your client application in one call.
Using static API wrappers
Writing complex code that has to check if a meeting is active before trying to start recording, leading to brittle error handling.
Just ask the agent: 'Start recording for this meeting.' The MCP manages the state and executes start_recording only when appropriate.
When It Fits, When It Doesn't
Use this MCP if your workflow involves managing multiple states of real-time communication—specifically, scheduling rooms, tracking who's in them, starting/stopping recordings, or broadcasting live feeds. You need a single point of control that can execute complex sequences like: 'Create meeting -> Add participants -> Start recording.' Don't use this MCP if you only need to read simple data about users (use a general user management tool) or if your communication is entirely asynchronous and never involves real-time presence checks. If your needs are limited to just creating rooms, check if a simpler scheduling API suffices; but for full lifecycle control, this MCP is necessary.
Questions you might have
How do I set up webhooks with the Dyte MCP? +
You use create_webhook to define your event endpoints. This allows your agent to receive real-time updates—like knowing exactly when a meeting ends—without you having to constantly check the status.
Can I manage recordings with Dyte MCP? +
Yes. You can start and stop capture using start_recording and stop_recording. Afterward, use get_recording to retrieve details or download links for the completed files.
What if I need to add a participant mid-call? +
You just tell your agent. It executes add_participant and handles generating the required auth tokens so your frontend can connect the new user immediately.
Does Dyte MCP handle live streaming? +
It does. You use start_livestream to begin broadcasting a meeting, and when you're finished, stop_livestream ends the broadcast cleanly.
What is the difference between get_meeting and list_meetings? +
Use list_meetings if you want to see all meetings associated with your organization. Use get_meeting when you know the ID of one specific meeting and need its current, detailed status.
We've already built the connector for Dyte. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 11 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.